Pushing the frontier of multimodal intelligence in Gemini. Director, Research Scientist at https://xitter.cf/t.co/osxwuzykCr.
Zurich, Switzerland
Joined December 2018
- Tweets530
- Following281
- Followers3K
- Likes5.3K
Pinned Tweet
Massive advancements in video understanding with Gemini 2.5! ✨ Unlock new capabilities to process hours of video, summarize and retrieve key moments, generate animations, and even combine video with code for interactive experiences. Check the 🧵below for some cool use-cases.
Thrilled to share our latest advances in video understanding 📽️: Gemini 2.5 Pro is a truly magical model to play with, excelling in traditional video analysis and unlocking new use cases I could not imagine a few months ago🪄
More in 🧵 and @Google blog: developers.googleblog.com/en…
Mario Lucic retweeted
The moment you've been waiting 4…
Our new frontier model, Gemini 4 Argon, is rolling out now in the Gemini app to bring your most complex ideas into reality.
See how Gemini 4 Argon and our latest updates across the Gemini app help you get the most out of every prompt. 🧵
Mario Lucic retweeted
Introducing Gemini 4 Argon – our new frontier model.
It’s built for complex workflows across coding, enterprise knowledge work, and cybersecurity defense – rolling out today to a set of trusted testers through our Fairwind Program.
Mario Lucic retweeted
Say hello (literally) to Gemini 3.8 Live and 3.8 Live Extended Thinking, our new SOTA live audio models, available with frontier price + performance.
3.8 Live supports 97 languages (can seamlessly switch), async tool calls, and more!
Mario Lucic retweeted
We’re introducing Gemini 3.8 Live and 3.8 Live Extended Thinking – our best conversational AI.
The models talk, think, and handle tasks in the background without breaking your flow. 🧵
Mario Lucic retweeted
We’re hiring! This is a rare opportunity to work with the folks that built Veo, Genie, and Gemini Omni — and advance the frontier of world models.
More details below 👇
Mario Lucic retweeted
Gemini with agentic video understanding is great at helping you create and edit video content. I made yesterday's music video in 30 mins: Gemini analysed my song -> suggested video themes -> made the storyboards & video prompts -> critiqued my draft edit. Some prompts to try: 🧵
Mario Lucic retweeted
between today and yesterday, we launched two amazing new capabilities: Gemini 3.8 Flash and Agentic Video Understanding and they have been so much fun to build with.
to test their limits, I built a retro Windows 98-themed workstation where you can drop in any YouTube URL of full 2-hour soccer matches 💾 ⚽(or any sports broadcast) & ask super detailed questions like "show me all the 🟨 yellow cards & bookings"
⚡ Agentic Video Understanding autonomously navigates across the 120-minute video timeline (no giant downloads or blind frame sampling)
🔍 dynamically zooms into candidate segments to detect referee whistles, tackles & card gestures
📍 isolates every card with exact sub-second timestamps & 2D pitch coordinates
🎬 pops out a tactical ledger where clicking any row instantly seeks and plays live!
no manual scrubbing. pure interactive video intelligence.
Mario Lucic retweeted
this agentic video understanding with Gemini based experiment got a lot of reactions & questions, will share a repo soon, so you can try it out. I have more examples coming in the next few days. there are so many possibilities with this model !!! 👾📹
Mario Lucic retweeted
Gemini video understanding is truly bonkers 🤯
Given a 2 hour football match, it scans the video for yellow cards, finds them, 3.8 Flash adds them to a 2D field so you can see where they occurred, then you can click on it and go to the exact part of the video!
Check it out 👇
between today and yesterday, we launched two amazing new capabilities: Gemini 3.8 Flash and Agentic Video Understanding and they have been so much fun to build with.
to test their limits, I built a retro Windows 98-themed workstation where you can drop in any YouTube URL of full 2-hour soccer matches 💾 ⚽(or any sports broadcast) & ask super detailed questions like "show me all the 🟨 yellow cards & bookings"
⚡ Agentic Video Understanding autonomously navigates across the 120-minute video timeline (no giant downloads or blind frame sampling)
🔍 dynamically zooms into candidate segments to detect referee whistles, tackles & card gestures
📍 isolates every card with exact sub-second timestamps & 2D pitch coordinates
🎬 pops out a tactical ledger where clicking any row instantly seeks and plays live!
no manual scrubbing. pure interactive video intelligence.
Mario Lucic retweeted
Introducing Gemini 3.8 Flash, another jump in Gemini's agentic + coding capabilities, and our 3rd updated Flash model in only 6 weeks...
This model has been a ton of fun to work with, excited to see what you all think!
Mario Lucic retweeted
introducing agentic video understanding with Gemini
instead of using static processing (ingesting media at a fixed frame rate), the model can now take an active, goal-directed role in determining what to watch, at what speed, and through which modality (frames, audio, or transcript), fetching only the moments and signals needed
this new approach cuts costs by up to 66% and reduces token consumption by up to 88% while boosting accuracy
available now via the Gemini API and in AI Studio: ai.studio
Mario Lucic retweeted
Introducing Agentic Video in the Gemini API, a new way to process long videos which reduces token consumption by up to 88% while also increasing quality.
This can be controlled easily in the API on a per video basis, available with our newest models like 3.7 Flash!
Mario Lucic retweeted
Today we're launching Gemini 3.7 Flash - our latest workhorse model for coding and agentic workflows, with an introductory price at half the original cost of 3.6 Flash. ⚡️
We have been iterating rapidly with the Flash series, going from 3.5 to 3.7 in just 3 months, making it more helpful across a wide range of tasks:
• Software Engineering (DeepSWE v1.1): 37.0% ➔ 65.3%
• Web Development (Code Arena Elo): 1506 ➔ 1588
• Enterprise Automation (AutomationBench): 13.4% ➔ 30.4%
Mario Lucic retweeted
Celebrating the milestone of a massive 150+ million downloads of Gemma 4 with the release of the new Gemma 4 12B model! It's incredibly powerful for such a small model and it’s tiny enough to run locally on a laptop with just 16GB VRAM. Apache 2.0 license - happy building!
